LATIDIA · Robótica

Navegación incorporada GPT-6-Astra Lights Up: evaluación en navegación de visión y lenguaje de disparo cero en entornos continuos

arXiv:2609.29861v2 Tipo de anuncio: reemplazar Resumen: Investigamos si GPT-6-Astra, un modelo de base de propósito general, puede navegar en entornos desconocidos utilizando su propia percepción, razonamiento y toma de decisiones ca

La noticia

arXiv:2609.29861v2 Announce Type: replace Abstract: We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and decision-making capabilities. Our evaluation focuses on zero-shot vision-and-language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for navigation. Using monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four key findings and implications. First, GPT-6-Astra achieves strong zero-shot navigation performance using only monocular RGB observations. On R2R-CE-100, GPT-6-Astra (ultra reasoning) achieves a success rate of 81.3%,